Added documentation to relevant modules

Author: kjaisingh

website/docs/modules/generate_batch_metrics.md

@@ -64,6 +64,13 @@ too slow.
 #### `ped_file`
 Family structures and sex assignments determined in [EvidenceQC](./eqc). See [PED file format](/docs/gs/inputs#ped-format).
 
+#### <HighlightOptionalArg>Optional</HighlightOptionalArg> `outlier_sample_ids`
+Provide a file containing sample IDs, delimited by new lines, to exclude from the generation of batch metrics - 
+this should can be based on outlier samples identified during sample QC that are still retained in the cohort. If 
+provided, the workflow discards any outlier samples from being considered as part of the called samples when 
+calculating metrics at a given site, as long as non-outlier samples are also called for that site. It does the 
+same for the set of background samples considered in the metric calculations for a given site.
+
 ## Outputs
 
 #### `metrics`

website/docs/modules/train_gcnv.md

@@ -71,6 +71,11 @@ Per-sample binned read counts (`*.rd.txt.gz`) generated in the [GatherSampleEvid
 Provide one of these inputs to subset the input batch. `n_samples_subsample` will randomly subset, while 
 `sample_ids_training_subset` is for defining a predetermined subset. These options are provided for convenience in Terra.
 
+#### <HighlightOptionalArg>Optional</HighlightOptionalArg> `outlier_sample_ids`
+Provide a file containing sample IDs, delimited by new lines, to exclude from the from the gCNV model training 
+process - this should can be based on outlier samples identified during sample QC that are still retained in the 
+cohort.
+
 ## Outputs
 
 #### `cohort_contig_ploidy_model_tar`